JavaScript Benchmark and more

classic Classic list List threaded Threaded
6 messages Options
Reply | Threaded
Open this post in threaded view
|

JavaScript Benchmark and more

DQ-3
Results were astonishing: latest Chrome (7.0.517.17) at 352ms, Opra
10.62 at 367ms, and latest Minefield 32bit [with hardware acceleration
enabled] at 502ms, while the 64bit Minefield browser [with hardware
acceleration enabled] (latest) measured 631.4ms! (link below),
especially because my system is high-end (Quad core 2.66Ghz, 3MB
cache, 4GB DDR3 RAM with Vista 6bit) and 4the MOZdev team boasts FF4b
to be fast.

http://www2.webkit.org/perf/sunspider-0.9/sunspider-results.html?%7B%223d-cube%22:%5B34,35,35,35,35%5D,%223d-morph%22:%5B15,16,15,15,16%5D,%223d-raytrace%22:%5B45,43,42,43,42%5D,%22access-binary-trees%22:%5B9,120,10,9,9%5D,%22access-fannkuch%22:%5B23,24,22,23,26%5D,%22access-nbody%22:%5B9,8,9,8,9%5D,%22access-nsieve%22:%5B8,8,9,8,9%5D,%22bitops-3bit-bits-in-byte%22:%5B1,1,1,1,1%5D,%22bitops-bits-in-byte%22:%5B11,11,11,11,11%5D,%22bitops-bitwise-and%22:%5B3,3,3,2,3%5D,%22bitops-nsieve-bits%22:%5B7,7,7,7,7%5D,%22controlflow-recursive%22:%5B6,6,6,6,6%5D,%22crypto-aes%22:%5B24,26,24,24,24%5D,%22crypto-md5%22:%5B10,10,10,10,9%5D,%22crypto-sha1%22:%5B5,5,5,5,5%5D,%22date-format-tofte%22:%5B33,33,33,33,158%5D,%22date-format-xparb%22:%5B207,37,36,36,36%5D,%22math-cordic%22:%5B16,16,15,16,16%5D,%22math-partial-sums%22:%5B13,14,13,13,14%5D,%22math-spectral-norm%22:%5B11,12,12,11,12%5D,%22regexp-dna%22:%5B42,45,46,42,46%5D,%22string-base64%22:%5B6,6,6,6,6%5D,%22string-fasta%22:%5B22,22,
 21,21,22%5D,%22string-tagcloud%22:%5B30,149,30,145,30%5D,%22string-unpack-code%22:%5B47,47,47,47,47%5D,%22string-validate-input%22:%5B12,12,124,12,12%5D%7D

its amazing really, how Opera, with LESS market share, is having
Mozilla run for its life! Also, Opera has added numerous high-demand
UI features, like consolidated menu, tabs in title bar, bookmarks/
downloads/history on toggle, and more.

Even after SIX betas and nightly  updates, MOZdev has barely  shed any
light on these issues.

So, Mozilla, what gives?
_______________________________________________
dev-performance mailing list
[hidden email]
https://lists.mozilla.org/listinfo/dev-performance
Reply | Threaded
Open this post in threaded view
|

Re: JavaScript Benchmark and more

Boris Zbarsky
On 9/25/10 9:00 PM, DQ wrote:
> Results were astonishing

They were?

> latest Chrome (7.0.517.17) at 352ms, Opra 10.62 at 367ms, and latest Minefield 32bit [with hardware acceleration
> enabled]  at 502ms, while the 64bit Minefield browser [with hardware
 > acceleration enabled] (latest) measured 631.4ms! (link below),

You're running sunspider.  Hardware acceleration is irrelevant.

Why is any of this astonishing?  http://arewefastyet.com/ has all this data.

> especially because my system is high-end (Quad core 2.66Ghz, 3MB
> cache, 4GB DDR3 RAM with Vista 6bit) and 4the MOZdev team boasts FF4b
> to be fast.

You seem to think that "fast" is a one-dimensional absolute metric.

The Fx4 betas are generally much faster than Fx 3.6.

On some tasks, the Fx4 betas are much faster than Opera or Chrome.

On some tasks, the Fx4 betas are much slower than Opera or Chrome.

And in fact, the same will probably be true for the final release.  Some
things will be faster; some will be slower.  It's up to you whether the
things that matter to you personally are performance of web apps or
execution time of a buggy benchmark that has code that's specifically
designed to make some browsers run slower by executing different tasks
in different browsers.

> So, Mozilla, what gives?

Bogus expectations on your end?  ;)

-Boris

_______________________________________________
dev-performance mailing list
[hidden email]
https://lists.mozilla.org/listinfo/dev-performance
Reply | Threaded
Open this post in threaded view
|

Re: JavaScript Benchmark and more

Boris Zbarsky
In reply to this post by DQ-3
On 9/25/10 9:00 PM, DQ wrote:
> its amazing really, how Opera, with LESS market share, is having
> Mozilla run for its life!

One other note.  It's amazing, really, how Opera, with more money and
more employees last I checked, has less market share....

-Boris
_______________________________________________
dev-performance mailing list
[hidden email]
https://lists.mozilla.org/listinfo/dev-performance
Reply | Threaded
Open this post in threaded view
|

Re: JavaScript Benchmark and more

DQ-3
@Boris

minefield x64: http://dromaeo.com/?id=118624
chrome 7.0.5171.17dev: http://dromaeo.com/?id=118625

apart from js performance, there's several UI features  ( tabs in
titlebar, single menu pane, etc.) that need to addressed. stylish may
have worked around some, but native implementation not only addresses
overall browser performance, but also code-level is better, i think.

i only wish ff4 to be superior.
_______________________________________________
dev-performance mailing list
[hidden email]
https://lists.mozilla.org/listinfo/dev-performance
Reply | Threaded
Open this post in threaded view
|

Re: JavaScript Benchmark and more

Boris Zbarsky
On 9/28/10 12:53 PM, DQ wrote:
> @Boris
>
> minefield x64: http://dromaeo.com/?id=118624
> chrome 7.0.5171.17dev: http://dromaeo.com/?id=118625

You're not telling me anything I don't know here.... ;)

-Boris
_______________________________________________
dev-performance mailing list
[hidden email]
https://lists.mozilla.org/listinfo/dev-performance
Reply | Threaded
Open this post in threaded view
|

Re: JavaScript Benchmark and more

Dave Mandelin-2
In reply to this post by DQ-3
On 9/25/2010 6:00 PM, DQ wrote:
> Results were astonishing: latest Chrome (7.0.517.17) at 352ms, Opra
> 10.62 at 367ms, and latest Minefield 32bit [with hardware acceleration
> enabled] at 502ms, while the 64bit Minefield browser [with hardware
> acceleration enabled] (latest) measured 631.4ms! (link below),
> especially because my system is high-end (Quad core 2.66Ghz, 3MB
> cache, 4GB DDR3 RAM with Vista 6bit) and 4the MOZdev team boasts FF4b
> to be fast.

[snip giant results URL.]

These results are a bit strange. For one, I noticed that the URL refers
to SunSpider 0.9, while the latest version is SunSpider 0.9.1. At least
one test in 0.9, regexp-dna, unfairly penalized Firefox because it used
an extension to the regexp replace API that only does something on Firefox.

So, you might want to run again with 0.9.1 and see how that looks. Last
time I ran SunSpider on a TM nightly (a week or 2 ago), we were 20%
slower than Chrome. It should already be even better than that.

On the x64 issue, we prioritized x86 performance, so making x64 fast is
going to take a little longer. Major improvements have been landing
there recently.

> its amazing really, how Opera, with LESS market share, is having
> Mozilla run for its life! Also, Opera has added numerous high-demand
> UI features, like consolidated menu, tabs in title bar, bookmarks/
> downloads/history on toggle, and more.

I don't know anything about Opera's resources or constraints so I can't
address this.

> Even after SIX betas and nightly  updates, MOZdev has barely  shed any
> light on these issues.
>
> So, Mozilla, what gives?

I don't think that's true. I (and other JS devs) have blogged and
tweeted all year about what we're doing and what kind of progress we're
making. Bugzilla shows a list of all the performance problems that need
investigation or are being worked on.

Dave
_______________________________________________
dev-performance mailing list
[hidden email]
https://lists.mozilla.org/listinfo/dev-performance